© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18371
    Prev
    Next
    INDEX
    Explanations

    checking status or correctness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -modal
    -0.08
     saga
    -0.08
     personality
    -0.08
    inke
    -0.08
    vg
    -0.08
     contradiction
    -0.08
     Bain
    -0.07
     merry
    -0.07
    bung
    -0.07
     scramble
    -0.07
    POSITIVE LOGITS
     status
    0.22
     progress
    0.21
     readiness
    0.21
     integrity
    0.21
     correctness
    0.19
     cleanliness
    0.19
     suitability
    0.19
     adequ
    0.19
    æĺ¯åIJ¦
    0.19
     validity
    0.19
    Activations Density 0.204%

    No Known Activations